Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sea
    -0.07
    :\/\/
    -0.06
    _c
    -0.06
    �
    -0.06
     NUM
    -0.06
     ration
    -0.06
    。在
    -0.06
    _HEAD
    -0.06
     intptr
    -0.05
    /h
    -0.05
    POSITIVE LOGITS
    (Application
    0.07
    ainted
    0.07
    �
    0.07
    kyně
    0.07
    Complete
    0.06
     Burning
    0.06
     giveaways
    0.06
    ardo
    0.06
     Zinc
    0.06
     Aura
    0.06
    Act Density 0.004%

    No Known Activations